AI engineering glossary · Deep learning core
What is forward pass?
Forward pass (also called Forward propagation): The step in which an input is pushed through the network layer by layer to produce an output and, during training, a loss value. No weights change during it; it just computes predictions using the current weights and stores intermediate values needed later.
Forward pass: an example
Feeding a batch of 32 images through the network to get 32 sets of class scores is one forward pass.
Related terms
- Backward pass
- Backpropagation
- Loss function
More Deep learning core terms
- Fully connected layer
- Gated linear unit
- Gating mechanism
- GELU
- Gradient checkpointing
- Gradient norm
- Group normalisation
- GRU
Where you learn it
Forward pass is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.